Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43193
    Prev
    Next
    INDEX
    Explanations

    phase detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kung
    -0.09
     dinner
    -0.08
     Dinner
    -0.08
     Everett
    -0.08
    -d
    -0.08
    nee
    -0.08
     Angst
    -0.08
    peech
    -0.07
     Dominion
    -0.07
     dining
    -0.07
    POSITIVE LOGITS
    numero
    0.08
    UILayout
    0.08
     kiek
    0.08
    Parsed
    0.08
     poste
    0.08
     geren
    0.07
     legado
    0.07
    #",
    0.07
     homolog
    0.07
     numero
    0.07
    Activations Density 0.001%

    No Known Activations